In the fields of artificial intelligence and robotics, the term “autonomy” is generally used to mean the capacity of an artificial agent to operate independently of human guidance. It is thereby assumed that the agent has a fixed goal or “utility function” with respect to which the appropriateness of its actions will be evaluated. From a philosophical perspective, this notion of autonomy seems oddly weak. For, in philosophy, the term is generally used to refer to a stronger capacity, namely the (...) capacity to “give oneself the law,” to decide by oneself what one’s goal or principle of action will be. The predominant view in the literature on the long-term prospects and risks of artificial intelligence is that an artificial agent cannot exhibit such autonomy because it cannot rationally change its own final goal, since changing the final goal is counterproductive with respect to that goal and hence undesirable. The aim of this paper is to challenge this view by showing that it is based on questionable assumptions about the nature of goals and values. I argue that a general AI may very well come to modify its final goal in the course of developing its understanding of the world. This has important implications for how we are to assess the long-term prospects and risks of artificial intelligence. (shrink)

Whether it would take one decade or several centuries, many agree that it is possible to create a *superintelligence*---an artificial intelligence with a godlike ability to achieve its goals. And many who have reflected carefully on this fact agree that our best hope for a "friendly" superintelligence is to design it to *learn* values like ours, since our values are too complex to program or hardwire explicitly. But the value learning approach to AI safety faces three particularly philosophical puzzles: first, (...) it is unclear how any intelligent system could learn its final values, since to judge one supposedly "final" value against another seems to require a further background standard for judging. Second, it is unclear how to determine the content of a system's values based on its physical or computational structure. Finally, there is the distinctly ethical question of which values we should best aim for the system to learn. I outline a potential answer to these interrelated puzzles, centering on a "miktotelic" proposal for blending a complex, learnable final value out of many simpler ones. (shrink)

Human excellences such as intelligence, morality, and consciousness are investigated by philosophers as well as artificial intelligence researchers. One excellence that has not been widely discussed by AI researchers is practical wisdom, the highest human excellence, or the highest, seventh, stage in Dreyfus’s model of skill acquisition. In this paper, I explain why artificial wisdom matters and how artificial wisdom is possible (in principle and in practice) by responding to two philosophical challenges to building artificial wisdom systems. The result is (...) a conceptual framework that guides future research on creating artificial wisdom. (shrink)

Considering the popular framing of an artificial intelligence as a rational agent that always seeks to maximise its expected utility, referred to as its goal, one of the features attributed to such rational agents is that they will never select an action which will change their goal. Therefore, if such an agent is to be friendly towards humanity, one argument goes, we must understand how to specify this friendliness in terms of a utility function. Wolfhart Totschnig, argues in contrast that (...) a fully autonomous agent will have the ability to change its utility function and will do so guided by its values. This commentary examines computational accounts of goals, values and decision-making. It rejects the idea that a rational agent will never select an action that changes its goal but also argues that an artificial intelligence is unlikely to be purely rational in terms of always acting to maximise a utility function. It nevertheless also challenges the idea that an agent which does not change its goal cannot be considered fully autonomous. It does agree that values are an important component of decision-making and explores a number of reasons why. (shrink)

Brauchen Roboter moralische Kompetenz? Die Antwort lautet ja. Einerseits benötigen Roboter moralische Kompetenz, um unsere Welt aus Regeln, Vorschriften und Werten zu begreifen, andererseits um von ihrem Umfeld akzeptiert zu werden. Wie aber lässt sich moralische Kompetenz in Roboter implementieren? Welche philosophischen Herausforderungen sind zu erwarten? Und wie können wir uns und unsere Kinder auf Roboter vorbereiten, die irgendwann über moralische Kompetenz verfügen werden? André und Iga Maria Schmiljun skizzieren aus einer humanistisch-philosophischen Perspektive erste Antworten auf diese Fragen und entwickeln (...) einen didaktischen Einstieg in das Thema für die Grundschule. (shrink)